vLLM 是一个用于大型语言模型的推理和服务引擎。在 0.30.0 版本之前,Rust 前端的 中间件会将原始 HTTP 方法令牌作为 Prometheus 标签,记录到达已注册路由的请求。未认证的攻击者可以向未加防护的路由(如 )发送唯一的任意方法令牌,从而导致 Prometheus 的 函数永久地创建计数器(counter)和直方图(histogram)的标签集合。这些标签集合会持续增加进程的内存占用,并扩大 接口的响应体积,直到服务或监控路径因资源耗尽而不可用。该问题已在 0.30.0 版本中修复。
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
| Vendor | Product | Affected Versions | CPE | Subscribe |
|---|---|---|---|---|
| vllm-project | vllm | < 0.30.0 | - |
|
| # | POC Description | Source Link | Shenlong Link |
|---|
No public POC found.
Login to generate AI POC| CVE-2026-105753 | 6.5 MEDIUM | vLLM: Mirrored multimodal IPC caches desync after a rejected request — a later request reu |
| CVE-2026-105754 | 6.5 MEDIUM | vLLM: Scale-out disaggregated multimodal transport trusts caller-supplied features |
| CVE-2026-105756 | 6.5 MEDIUM | vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP de |
| CVE-2026-105757 | 6.5 MEDIUM | vLLM: Structured-output request errors escape the request boundary and terminate the share |
| CVE-2026-105760 | 5.3 MEDIUM | vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion |
| CVE-2026-105758 | 5.3 MEDIUM | vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the |
| CVE-2026-105755 | 4.2 MEDIUM | vLLM: Flash late-interaction scoring caches query embeddings under a caller-controlled req |
| CVE-2026-105752 | 3.1 LOW | vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache |
No comments yet